Model profile / Alibaba Cloud

Qwen3.8-27B

Qwen's open-weight 27B dense vision-language model with native 262,144-token context, extensible to 1,000,000 tokens, and configurable xhigh, medium and low reasoning effort.

14 Aug 2026Open weightsProvider

Sources & details

Four areas of evidence

The capabilities behind the model.

How the indices work

Reasoning

112.0Index points

Mathematical and scientific problem solving.

This model│ Other models · 155 rated

Score and research range

Full-precision point: 112.04024297326077
Range: 109.42–114.66 · 90% Research Range
Scope: Conditional fuller R0 A

Score includes qualified prediction of missing evidence.

Coding

105.8Index points

Software engineering and programming.

This model│ Other models · 39 rated

Score and research range

Full-precision point: 105.81447098740483
Range: No qualified range available
Scope: Frozen Coding score under admitted comparison/reference/source reweighting

Score uses the admitted direct native evidence under the selected method.

General

48.2Index points

Factual reliability and instruction following.

This model│ Other models · 61 rated

Score and research range

Full-precision point: 48.22497222222223
Range: No qualified range available
Scope: General G4 under admitted instruction-task portfolio resampling conditional on exact recorded R and U

Score uses the admitted direct native evidence under the selected method.

Agentic

106.9Index points

Tool use, workflows and professional tasks.

This model│ Other models · 40 rated

Score and research range

Full-precision point: 106.87979274713798
Range: 105.25–108.33 · 90% Research Range
Scope: Agentic score under joint reference/source reweighting conditional on admitted W/X/P native outcomes

Score uses the admitted direct native evidence under the selected method.

19retained native records

13evidence families

Capabilities estimateQualified original evidence across four areas.

Current index snapshot · 2026-09-16. Each category uses its own scale; scores across categories are not directly comparable. Evidence counts describe the retained Capabilities inputs; a family can contain several tasks or configurations. A point lead does not establish superiority.

Performance in context

Capabilities, price & speed.

Explore every model

Qwen3.8-27B is highlighted wherever a compatible measurement is available.

Qwen3.8-27B: Regional/tier or mutable endpoint-to-checkpoint binding unresolved; no price inherited

Lumina Capabilities Index

Capabilities versus API price

The current Capabilities cohort, with this model highlighted.

Lumina

2025+ · 62 models · 1 highlighted

Chart loads as you explore

Qwen3.8-27B: No exact base-profile release and documented 10K output measurement; other effort/protocol/alias records not substituted

Lumina Capabilities Index

Capabilities versus output speed

The current Capabilities cohort, with this model highlighted.

Lumina

2025+ · 72 models · Developer API · 10K · 1 highlighted

Chart loads as you explore

Explore the detail

Sources & model details.

Original evidence, with its context.

Current index evidence 5Scores, research ranges and the sources behind each category.

Capabilities

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-27b
Method: methods-a4471cee84fd478d2ed3
Range interpretation: C1 native factor under conditional crossed source/family reweighting of admitted fixed-corpus reference and own portfolio
Sources: Artificial Analysis:Artificial Analysis · LiveBench:LiveBench
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Coding

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-27b
Method: methods-a4471cee84fd478d2ed3
Range interpretation: Frozen Coding score under admitted comparison/reference/source reweighting
Sources: Artificial Analysis · LiveBench
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Reasoning

Score includes qualified prediction of missing evidence.

Exact checkpoint: qwen-3-8-27b
Method: methods-a4471cee84fd478d2ed3
Range interpretation: Conditional fuller R0 A
Sources: aa
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Agentic

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-27b
Method: methods-a4471cee84fd478d2ed3
Range interpretation: Agentic score under joint reference/source reweighting conditional on admitted W/X/P native outcomes
Sources: Artificial Analysis
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

General

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-27b
Method: methods-a4471cee84fd478d2ed3
Range interpretation: General G4 under admitted instruction-task portfolio resampling conditional on exact recorded R and U
Sources: Artificial Analysis · LiveBench
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Benchmark measurements 57Published values in each benchmark’s own units.

57 measurements

Qwen3.8-27B published benchmark measurements
Benchmark	Result	Published configuration	Source
Agents Last ExamPass@1	20.4%	Qwen3.8-27B (xhigh)Qwen3.8-27B official text table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
Agents Last ExamScore	42.9%	Qwen3.8-27B (xhigh)Qwen3.8-27B official text table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
AndroidWorld2026	81.9%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
BabyVisionWith CI	85.6%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
BabyVisionWithout CI	65.7%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
Claw-EvalAverage	56.9%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
Claw-EvalPass@3	57.4%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
ERQA2026	65.5%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
JobBench2026	33.4%	Qwen3.8-27B (xhigh)Qwen3.8-27B official text table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
MathVisionWith CI	94.6%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only

Showing 10 of 57 measurements

Specifications & source recordsDocumented model details and original references.

Model ID / checkpoint: Qwen/Qwen3.8-27B
Weight access: Open weights
Context window: 262,144
Maximum output: Not documented
Modalities: text, image, video
Details checked: 31 Aug 2026

Qwen3.8-27B official model cardQwen · Published 14 Aug 2026 · checked 31 Aug 2026 · source-checked Qwen3.8-27B official repository metadataQwen · checked 22 Aug 2026 · source-checked Qwen3.8-Flash-Next launch and official provider evaluationsQwen · Published 26 Aug 2026 · checked 26 Aug 2026 · source-checked

Specialist task evidenceSeparate agent runs and execution conditions.

All models

Model profile / Alibaba Cloud

Qwen3.8-27B

Qwen's open-weight 27B dense vision-language model with native 262,144-token context, extensible to 1,000,000 tokens, and configurable xhigh, medium and low reasoning effort.

14 Aug 2026Open weightsProvider

Sources & details

Four areas of evidence

The capabilities behind the model.

How the indices work

Reasoning

112.0Index points

Mathematical and scientific problem solving.

This model│ Other models · 155 rated

Score and research range

Full-precision point: 112.04024297326077
Range: 109.42–114.66 · 90% Research Range
Scope: Conditional fuller R0 A

Score includes qualified prediction of missing evidence.

Coding

105.8Index points

Software engineering and programming.

This model│ Other models · 39 rated

Score and research range

Full-precision point: 105.81447098740483
Range: No qualified range available
Scope: Frozen Coding score under admitted comparison/reference/source reweighting

Score uses the admitted direct native evidence under the selected method.

General

48.2Index points

Factual reliability and instruction following.

This model│ Other models · 61 rated

Score and research range

Full-precision point: 48.22497222222223
Range: No qualified range available
Scope: General G4 under admitted instruction-task portfolio resampling conditional on exact recorded R and U

Score uses the admitted direct native evidence under the selected method.

Agentic

106.9Index points

Tool use, workflows and professional tasks.

This model│ Other models · 40 rated

Score and research range

Full-precision point: 106.87979274713798
Range: 105.25–108.33 · 90% Research Range
Scope: Agentic score under joint reference/source reweighting conditional on admitted W/X/P native outcomes

Score uses the admitted direct native evidence under the selected method.

19retained native records

13evidence families

Capabilities estimateQualified original evidence across four areas.

Performance in context

Capabilities, price & speed.

Explore every model

Qwen3.8-27B is highlighted wherever a compatible measurement is available.

Qwen3.8-27B: Regional/tier or mutable endpoint-to-checkpoint binding unresolved; no price inherited

Lumina Capabilities Index

Capabilities versus API price

The current Capabilities cohort, with this model highlighted.

Lumina

2025+ · 62 models · 1 highlighted

Chart loads as you explore

Qwen3.8-27B: No exact base-profile release and documented 10K output measurement; other effort/protocol/alias records not substituted

Lumina Capabilities Index

Capabilities versus output speed

The current Capabilities cohort, with this model highlighted.

Lumina

2025+ · 72 models · Developer API · 10K · 1 highlighted

Chart loads as you explore

Explore the detail

Sources & model details.

Original evidence, with its context.

Current index evidence 5Scores, research ranges and the sources behind each category.

Capabilities

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-27b
Method: methods-a4471cee84fd478d2ed3
Range interpretation: C1 native factor under conditional crossed source/family reweighting of admitted fixed-corpus reference and own portfolio
Sources: Artificial Analysis:Artificial Analysis · LiveBench:LiveBench
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Coding

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-27b
Method: methods-a4471cee84fd478d2ed3
Range interpretation: Frozen Coding score under admitted comparison/reference/source reweighting
Sources: Artificial Analysis · LiveBench
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Reasoning

Score includes qualified prediction of missing evidence.

Exact checkpoint: qwen-3-8-27b
Method: methods-a4471cee84fd478d2ed3
Range interpretation: Conditional fuller R0 A
Sources: aa
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Agentic

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-27b
Method: methods-a4471cee84fd478d2ed3
Range interpretation: Agentic score under joint reference/source reweighting conditional on admitted W/X/P native outcomes
Sources: Artificial Analysis
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

General

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-27b
Method: methods-a4471cee84fd478d2ed3
Range interpretation: General G4 under admitted instruction-task portfolio resampling conditional on exact recorded R and U
Sources: Artificial Analysis · LiveBench
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Benchmark measurements 57Published values in each benchmark’s own units.

57 measurements

Qwen3.8-27B published benchmark measurements
Benchmark	Result	Published configuration	Source
Agents Last ExamPass@1	20.4%	Qwen3.8-27B (xhigh)Qwen3.8-27B official text table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
Agents Last ExamScore	42.9%	Qwen3.8-27B (xhigh)Qwen3.8-27B official text table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
AndroidWorld2026	81.9%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
BabyVisionWith CI	85.6%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
BabyVisionWithout CI	65.7%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
Claw-EvalAverage	56.9%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
Claw-EvalPass@3	57.4%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
ERQA2026	65.5%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
JobBench2026	33.4%	Qwen3.8-27B (xhigh)Qwen3.8-27B official text table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only
MathVisionWith CI	94.6%	Qwen3.8-27B (xhigh)Qwen3.8-27B official VL table	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15provider-reported · reference-only

Showing 10 of 57 measurements

Specifications & source recordsDocumented model details and original references.

Model ID / checkpoint: Qwen/Qwen3.8-27B
Weight access: Open weights
Context window: 262,144
Maximum output: Not documented
Modalities: text, image, video
Details checked: 31 Aug 2026

Specialist task evidenceSeparate agent runs and execution conditions.

The capabilities behind the model.

Capabilities, price & speed.

Capabilities versus API price

Capabilities versus output speed

Sources & model details.

Capabilities

Coding

Reasoning

Agentic

General

More from Alibaba Cloud.

Qwen3.8-Flash-Next

Qwen3.6 Plus

Qwen3.5-122B-A10B

The capabilities behind the model.

Capabilities, price & speed.

Capabilities versus API price

Capabilities versus output speed

Sources & model details.

Capabilities

Coding

Reasoning

Agentic

General

More from Alibaba Cloud.

Qwen3.8-Flash-Next

Qwen3.6 Plus

Qwen3.5-122B-A10B